A contextual combinatorial multi-armed bandit with attention-based probing and early stopping is proposed for joint access-point and beam selection in mmWave networks, with a claimed O(T^{3/4} log T) regret bound.
Contextual combinatorial multi-armed bandits with volatile arms and submodular reward,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
extension 1
citation-polarity summary
fields
cs.NI 1years
2024 1verdicts
REJECT 1roles
extension 1polarities
extend 1representative citing papers
citing papers explorer
-
Contextual Combinatorial Beam Management via Online Probing for Multiple Access mmWave Wireless Networks
A contextual combinatorial multi-armed bandit with attention-based probing and early stopping is proposed for joint access-point and beam selection in mmWave networks, with a claimed O(T^{3/4} log T) regret bound.